Corpora and Statistical Methods

1 / 108

# Corpora and Statistical Methods - PowerPoint PPT Presentation

Corpora and Statistical Methods. Albert Gatt. In this lecture. Introduction to Natural Language Generation (NLG ) the use of corpora & statistical models in NLG Summarisation Single-document Multi-document Evaluation using corpora: BLEU/NIST/ROUGE and related metrics. Part 1.

I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.

## Corpora and Statistical Methods

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.

- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
1. Corpora and Statistical Methods Albert Gatt

2. In this lecture • Introduction to Natural Language Generation (NLG) • the use of corpora & statistical models in NLG • Summarisation • Single-document • Multi-document • Evaluation using corpora: BLEU/NIST/ROUGE and related metrics

3. Part 1 Natural Language Generation

4. What is NLG? • NLG systems aim to produce understandable texts (in English or other languages) typically from non-linguisticinput. Examples: • Automatic generation of weather reports. • Input: data in the form of numbers (Numerical Weather Prediction models) • Output: short text representing a weather forecast • Many systems developed in this domain. • STOP: • generates smoking cessation letters based on a user-input questionnaire • http://www.csd.abdn.ac.uk/research/stop/

5. Weather report example S 8-13 increasing 18-23 by morning, then easing 8-13 by midnight. S 8-13 increasing 13-18 by early morning, then backing NNE 18-23 by morning, and veering S 13-18 by midday, then easing 8-13 by midnight. SUMTIME: http://cgi.csd.abdn.ac.uk/~ssripada/cgi_bin/startSMT.cgi

6. NLG in dialogue systems Dialogue fragment: • System1: Welcome.... What airport would you like to fly out of? • User2: I need to go to Dallas. • System3: Flying to Dallas. What departure airport was that? • User4: from Newark on September the 1st. What should the system say next? Plan for next utterance (after analysis of User4) implicit-confirm(orig-city:NEWARK) implicit-confirm(dest-city:DALLAS) implicit-confirm(month:9) implicit-confirm(day-number:1) request(depart-time) Output next uttterance: • What time would you like to travel on September the 1st to Dallas from Newark? Walker et al. (2001). SPoT: A trainable sentence planner. Proc. NAACL

7. Types of input to an NLG system • Raw data (e.g. Weather report systems): • Typical of data-to-text systems • These systems need to pre-analyse the data • Knowledge base: • Symbolic information (e.g. database of available flights) • Content plan: • representation of what to communicate (usually in some canonical representation) • e.g.: complete story plan (STORYBOOK) • Other sources: • Discourse/dialogue history • Keep track of what’s been said to inform planning

8. The architecture of NLG systems • A pipeline architecture • represents a “consensus” of what NLG systems actually do • very modular • not all implemented systems conform 100% to this architecture Communicative goal Document Planner (Content selection) document plan Microplanner (text planner) text specification Surface Realiser text

9. Concrete example • BabyTalk systems (Portet et al 2009) • summarise data about a patient in a Neonatal Intensive Care Unit • main purpose: generate a summary that can be used by a doctor/nurse to make a clinical decision F. Portet et al (2009). Automatic generation of textual summaries from neonatal intensive care data. Artificfial Intelligence

10. A micro example Input data: unstructured raw numeric signal from patient’s heart rate monitor (ECG) There were 3 successive bradycardias down to 69.

11. A micro example: pre-NLG steps (1) Signal Analysis (pre-NLG) • Identify interesting patterns in the data. • Remove noise. (2) Data interpretation (pre-NLG) • Estimate the importance of events • Perform linking & abstraction

12. Document planning/Content Selection • Main tasks • Content selection • Information ordering • Typical output is a document plan • tree whose leaves are messages • nonterminals indicate rhetorical relations between messages (Mann & Thompson 1988) • e.g. justify, part-of, cause, sequence…

13. A micro example: Document planning (1) Signal Analysis (pre-NLG) • Identify interesting patterns in the data. • Remove noise. (2) Data interpretation (pre-NLG) • Estimate the importance of events • Perform linking & abstraction (3) Document planning • Select content based on importance • Structure document using rhetorical relations • Communicative goals (here: assert something)

14. A micro example: Microplanning • Lexicalisation • Many ways to express the same thing • Many ways to express a relationship • e.g. SEQUENCE(x,y,z) • x happened, then y, then z • x happened, followed by y and z • x,y,z happened • there was a sequence of x,y,z • Many systems make use of a lexical database.

15. A micro example: Microplanning • Aggregation: • given 2 or more messages, identify ways in which they could be merged into one, more concise message • e.g. be(HR, stable) + be(HR, normal) • (No aggregation) HR is currently stable. HR is within the normal range. • (conjunction) HR is currently stable and HR is within the normal range. • (adjunction) HR is currently stable within the normal range.

16. A micro example: Microplanning • Referring expressions: • Given an entity, identify the best way to refer to it • e.g. BRADYCARDIA • bradycardia • it • the previous one • Depends on discourse context! (Pronouns only make sense if entity has been referred to before)

17. A micro example (4) Microplanning Map events to semantic representation • lexicalise: bradycardia vs sudden drop in HR • aggregate multiple messages (3 bradycardias = one sequence) • decide on how to refer (bradycardia vs it)

18. A micro example: Realisation • Subtasks: • map the output of microplanning to a syntactic structure • needs to identify the best form, given the input representation • typically many alternatives • which is the best one? • apply inflectional morphology (plural, past tense etc) • linearise as text string

19. s PRO VP (+past) PP NP (+pl) V there be three successive bradycardias down to 69 A micro example (4) Microplanning Map events to semantic representation • lexicalise: bradycardia vs sudden drop in HR • aggregate multiple messages (3 bradycardias = one sequence) • decide on how to refer (bradycardia vs it) • choose sentence form (there were…) (5) Realisation • map semantic representations to syntactic structures • apply word formation rules

20. Rules vs statistics • Many NLG systems are rule-based • Growing trend to use statistical methods. • Main aims: • increase linguistic coverage (e.g. of a realiser) “cheaply” • develop techniques for fast building of a complete system

21. Using statistical methods Language models and realisation

22. Advantages of using statistics • Construction of NLG systems is extremely laborious! • e.g. BabyTalk system took ca. 4 years with 3-4 developers • Many statistical approaches focus on specific modules • best-studied: statistical realisation • realisers that take input in some canonical form and rely on language models to generate output • advantage: • easily ported to new domains/applications • coverage can be increased (more data/training examples)

23. Overgeneration and ranking • The approaches we will consider rely on “overgenerate-and-rank” approach: • Given: input specification (“semantics” or canonical form) • Use a simple rule-based generator to produce many alternative realisations. • Rank them using a language model. • Output the best (= most probable) realisation.

24. Advantages of overgeneration + ranking • There are usually many ways to say the same thing. • e.g. ORDER(eat(you,chicken)) • Eat chicken! • It is required that you eat chicken! • It is required that you eat poulet! • Poulet should be eaten by you. • You should eat chicken/chickens. • Chicken/Chickens should be eaten by you.

25. Where does the data come from? • Some statistical NLG systems were built based on parallel data/text corpora. • allows direct learning of correspondences between content and output • rarely available • Some work relies on Penn Treebank: • Extract input: process the treebank to extract “canonical specifications” from parsed sentences • train a language model • re-generate using a realiser and evaluate against original treebank

26. Extracting input from treebank • Penn treebank input: C. Callaway (2003). Evaluating coverage for large, symbolic NLG grammars. Proc. IJCAI

27. Extracting input from treebank • Converted into required input representation: C. Callaway (2003). Evaluating coverage for large, symbolic NLG grammars. Proc. IJCAI

28. Nitrogen and HALogen • Pioneering realisation systems with wide coverage (i.e. handle many phenomena of English grammar) • Based on overgeneration/ranking • HALogen (Langkilde-Geary 2002) is a successor to Nitrogen (Langkilde 1998) • main differences: • representation data structure for possible realisation alternatives • HALogen handles more grammatical features

29. Structure of HALogen • Symbolic Generator • Rules to map input representation to syntactic structures • Lexicon • Morphology multiple outputs represented in a “forest” • Statistical ranker • n-gram model (from Penn Treebank) best sentence

30. HALogen Input Grammatical specification (e1 / eat :subject (d1 / dog) :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today)) Semantic specification (e1 / eat :agent (d1 / dog) :patient (b1 / bone :premod(m1 / meaty)) :temp-loc(t1 / today)) • Labeled feature-value representation specifying properties and relations of domain objects (e1, d1, etc) • Recursively structured • Order-independent • Can be either grammatical or semantic (or mixture of both) • recasting mechanism maps from one to another

31. HALogen base generator • Consists of about 255 hand-written rules • Rules map an input representation into a packed set of possible output expressions. • Each part of the input is recursively processed by the rules, until only a string is left. • Types of rules: • recasting • ordering • filling • morphing

32. Recasting • Map semantic input representation to one that is closer to surface syntax. Semantic specification (e1 / eat :patient (b1 / bone :premod(m1 / meaty)) :temp-loc(t1 / today) :agent (d1 / dog)) IF relation = :agent AND sentence is not passive THEN map relation to :subject Grammatical specification (e1 / eat :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today) :subject (d1 / dog))

33. Ordering • Assign a linear order to the values in the input. Grammatical specification (e1 / eat :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today) :subject (d1 / dog)) Put subject first unless sentence is passive. Put adjuncts sentence-finally. Grammatical specification + order (e1 / eat :subject (d1 / dog) :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today))

34. Filling • If input is under-specified for some features, add all the possible values for them. • NB: this allows for different degrees of specification, from minimally to maximally specified input. • Can create multiple “copies” of same input +:TENSE (past) Grammatical specification + order (e1 / eat :subject (d1 / dog) :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today)) +:TENSE (present)

35. Morphing • Given the properties of parts of the input, add the correct inflectional features. Grammatical specification + order (e1 / eat :tense(past) :subject (d1 / dog) :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today)) Grammatical specification + order (e1 / ate :subject (d1 / dog) :object (b1 / bone :premod(m1 / meaty)) :adjunct(t1 / today))

36. The output of the base generator • Problem: • a single input may have literally hundreds of possible realisations after base generation • these need to be represented in an efficient way to facilitate search for the best output • Options: • word lattice • forest of trees

37. Option 1: lattice structure (Langkilde 2000) “You may have to eat chicken”: 576 possibilities!

38. Properties of lattices • In a lattice, a complete left-right path represents a possible sentence. • Lots of duplication! • e.g. the same word “chicken” occurs multiple times • ranker will be scoring the same substring more than once • In a lattice path, every word is dependent on all other words. • can’t model local dependencies

39. Option 2: Forests (Langkilde‘00,’02) S OR S.328 S.358 NP.318 VP.357 PRP.3 VP.327 PRP.3 VP.248 NP.318 you OR … to be eaten by … the chicken

40. Properties of forests • Efficient representation: • each individual constituent represented only once, with pointers • ranker will only compute a partial score for a subtree once • several alternatives represented by disjunctive (“OR”) nodes • Equivalent to a non-recursive context-free grammar • S.469  S.328 • S.469  S.358 • …

41. Statistical ranking • Uses n-gram language models to choose the best realisation r:

42. Performance of HALogen Minimally specified input frame (bigram model): • It would sell its fleet age of Boeing Co. 707s because of maintenance costs increase the company announced earlier. Minimally specified input frame (trigram model): • The company earlier announced it would sell its fleet age of Boeing Co. 707s because of the increase maintenance costs. Almost fully specified input frame: • Earlier the company announced it would sell its aging fleet of Boeing Co. 707s because of increased maintenance costs.

43. Observations • The usual issues with n-gram models apply: • bigger n better output, but more data sparseness • Domain dependent • relatively easy to train, assuming corpus in the right format

44. Evaluation How should an NLG system/module be evaluated?

45. Evaluation in NLG • Types of evaluation: • Intrinsic: evaluate output in its own right (linguistic quality etc) • Extrinsic: evaluate output in the context of a task with target users • Intrinsic evaluation of realisation output often relies on metrics like BLEU and NIST.

46. BLEU: Modified n-gram precision • Let t be a translation/generated text • Let {r1,…,rn} be a set of reference translations/texts • Let n be the maximum ngram value (usually 4) do for 1 to n: For each ngram in t: max_ref_count := max times it occurs in some r clipped_count := min(count,max_ref_count) score := total clipped counts/total unclipped counts • Scores for different ngrams are combined using a geometric mean. • A brevity penalty is added to the score to avoid favouring very short ngrams.

47. BLEU example (unigram) t = the thethethethethe r1 = the dog ate the meat pie r2 = the dog ate a meat pie • only one unigram (“the”) in t • max_ref_count = 2 • clipped_count = min(count, max_ref_count) = min(2,6) = 2 • score = clipped_count/count = 2/6

48. NIST: modified version of BLEU • A version of BLEU developed by the US National Institute of Standards and Technology. • Instead of just counting matching ngrams, weights counts by their informativeness • for any matching ngram between t and reference corpus, the rarer the ngram in the reference corpus the better

49. Alternative metrics • Some version of edit (Levenshtein) distance is often used. • score reflecting the no. of insertions (I), deletions (D) and substitutions (S) required to transform a string into another string. • NIST simple string accuracy (SSA): essentially average edit distance • SSA = 1-(I+D+S)/(length of sentence)

50. BLEU/NIST in NLG • HALogen’s output compared to reference Treebank outputs using BLEU/SSA. • Fully specified input: • output produced for ca. 83% of inputs • SSA = 94.5 • BLEU = 0.92 • Minimally specified input: • output produced for ca. 79.3% • SSA = 55.3 • BLEU = 0.51